Digital Commons Network^™

Cas: Fusing Dnn Optimization & Adaptive Sensing For Energy-Efficient Multi-Modal Inference, Dulanga Weerakoon, Vigneshwaran Subbaraju, Joo Hwee Lim, Archan Misra

Research Collection School Of Computing and Information Systems

Intelligent virtual agents are used to accomplish complex multi-modal tasks such as human instruction comprehension in mixed-reality environments by increasingly adopting richer, energy-intensive sensors and processing pipelines. In such applications, the context for activating sensors and processing blocks required to accomplish a given task instance is usually manifested via multiple sensing modes. Based on this observation, we introduce a novel Commit-and-Switch ( CAS ) paradigm that simultaneously seeks to reduce both sensing and processing energy. In CAS , we first commit to a low-energy computational pipeline with a subset of available sensors. Then, the task context estimated by this pipeline …

From Data To Application: Harnessing Big Spatial Data And Spatially Explicit Machine Learning Model For Landslide Susceptibility Prediction And Mapping, Min Naing Khant, Mei Yi Victoria Grace Ann, Tin Seong Kam

Research Collection School Of Computing and Information Systems

Recent advancements in information and communication technology have significantly enhanced access to extensive geospatial data, presenting a valuable opportunity to leverage big spatial data for improved modeling and predictive capabilities in natural disaster risk assessment. This paper explores the integration of a comprehensive dataset comprising historical landslide events and various geo-environmental variables within a spatially explicit machine learning framework. The study empirically demonstrates that incorporating big spatial data allows a more nuanced understanding of local variations and spatial dependencies. Ultimately, this empirical assessment produces more accurate landslide risk predictions than traditional baseline models. Using Italy’s expansive Valtellina Valley as a …

Revisiting The Conflict-Resolving Problem From A Semantic Perspective, Jinhao Dong, Jun Sun, Yun Lin, Yedi Zhang, Murong Ma, Jin Song Dong, Dan Hao

Research Collection School Of Computing and Information Systems

Collaborative software development significantly enhances development productivity by enabling multiple contributors to work concurrently on different branches. Despite these advantages, such collaboration often increases the likelihood of causing conflicts. Resolving these conflicts brings huge challenges, primarily due to the necessity of comprehending the differences between conflicting versions. Researchers have explored various automatic conflict resolution techniques, including unstructured, structured, and learning-based approaches. However, these techniques are mostly heuristic-based or black-box in nature, which means they do not attempt to solve the root cause of the conflicts, i.e., the existence of different program behaviors exhibited by the conflicting versions.In this work, we …

Hi3d: Pursuing High-Resolution Image-To-3d Generation With Video Diffusion Models, Haibo Yang, Yang Chen, Yingwei Pan, Ting Yao, Zhineng Chen, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Despite having tremendous progress in image-to-3D generation, existing methods still struggle to produce multi-view consistent images with high-resolution textures in detail, especially in the paradigm of 2D diffusion that lacks 3D awareness. In this work, we present High-resolution Image-to-3D model (Hi3D), a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation (i.e., orbital video generation). This methodology delves into the underlying temporal consistency knowledge in video diffusion model that generalizes well to geometry consistency across multiple views in 3D generation. Technically, Hi3D first empowers the pre-trained video diffusion model with 3D-aware …

Multimodal Misinformation Detection By Learning From Synthetic Data With Multimodal Llms, Fengzhu Zeng, Wenqian Li, Wei Gao, Yan Pang

Research Collection School Of Computing and Information Systems

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap. To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions. Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even …

Scoping Software Engineering For Ai: The Tse Perspective, Sebastián Uchitel, Marsha Chechik, Massimiliano Di Penta, Bram Adams, Nazareno Aguirre, Gabriele Bavota, Domenico Bianculli, Kelly Blincoe, Ana Cavalcanti, Yvonne Dittrich, Filomena Ferrucci, Rashina Hoda, Liguo Huang, David Lo, Et Al.

Research Collection School Of Computing and Information Systems

In recent years, important advances in Artificial Intelligence (AI), and, in particular, in Machine Learning (ML), including Deep Learning (DL) and Large Language Models (LLMs), have caused a substantial increase of submissions to all Software Engineering (SE) venues (conferences and journals) related to SE with and for AI. They are commonly referred to as AI for SE and SE for AI.

Thoughts To Target: Enhance Planning For Target-Driven Conversation, Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie

Research Collection School Of Computing and Information Systems

In conversational AI, large-scale models excel in various tasks but struggle with target-driven conversation planning. Current methods, such as chain-of-thought reasoning and tree-search policy learning techniques, either neglect plan rationality or require extensive human simulation procedures. Addressing this, we propose a novel two-stage framework, named EnPL, to improve the LLMs’ capability in planning conversations towards designated targets, including (1) distilling natural language plans from target-driven conversation corpus and (2) generating new plans with demonstration-guided in-context learning. Specifically, we first propose a filter approach to distill a high-quality plan dataset, ConvPlan1. With the aid of corresponding conversational data and support from …

Yellow Crazy Ant, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

Yellow crazy ants (Anoplolepis gracilipes) are believed to be native to west Africa or Asia. They are not present in Western Australia (WA) and are prohibited.

Yellow crazy ants were first observed in Australia in the early 1900’s on the Cocos-Keeling Islands and Christmas Island, where they have now caused a massive decline in the population of iconic red crabs. More recently, they have been recorded in Queensland, the Northern Territory (NT), and New South Wales (NSW).

Rabbit Control: Warren And Harbourage Destruction, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

If correctly and appropriately undertaken, the destruction of rabbit warrens, or modification of the habitat so it becomes less favourable to rabbits, can be an important and effective part of reducing the impacts of rabbits.

Destruction of warrens can improve the overall effectiveness of rabbit control programs, even though many rabbits live and shelter above-ground under bushes, and in scrub). If undertaken properly, the ripping of rabbit warrens can often provide a relatively permanent and long-term benefit. Similarly, removing or modifying other forms of rabbit-harbourage (for example, removing rock piles) can help, particularly in semi-urban areas or on smallholdings.

Rabbit Control In Urban And Semi-Urban Areas, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

This factsheet provides information on control options for rabbits in urban and semi-urban areas in Western Australia (WA).

Rabbits cause considerable losses to agricultural and horticultural industries. They can cause serious environmental problems, such as soil erosion and degradation of native vegetation. Rabbits also compete with native fauna for food and habitat.

Rabbits may be a problem or a nuisance in urban environments where they can damage lawns and gardens, buildings, garages, and sheds. Rabbits can also damage golf courses, sports grounds, and parkland reserves.

The options for control of rabbits in urban areas are more limited than in rural …

Water Lettuce And Its Control, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

Water lettuce (Pistia stratiotes) is a declared pest in Western Australia (WA). This factsheet describes the nature of the plant with links to requirements landowners/occupiers must adhere to and pest control methods.

Adopt-A-Trap To Help Detect European Wasps, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

Early detection of European wasp is important to prevent the spread and establishment of nests, and the Adopt-a-trap program is a key part of annual European wasp surveillance.

The department intensively traps the highest risk areas of the state, but the Adopt-a-trap program can extend surveillance beyond these areas and into the regions to enhance community surveillance.

The trapping method used in the Adopt-a-trap program is very successful in catching European wasps. They address the wasps’ sense of smell and foraging habits to find food. Trapped wasps are useful in alerting us to the presence of a nearby nest — …

Argentine Ants, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

Argentine ants (Linepithema humile) are small, brown, and notorious worldwide for being one of the most difficult and costly ants to control, as it can involve ongoing and repetitive use of residual, contact insecticides. The ants are established in Western Australia (WA).

Electric Ant (Little Fire Ant), Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

The electric ant (Wasmannia auropunctata), also known as little fire ant, is a tiny, gold-brown coloured ant, and one of the world's most invasive pests. Electric ants prey on and compete with other insects and can displace large numbers of native animals, ants, and other insects.

They affect human health and lifestyle, can inflict painful stings on humans and wild and domestic animals, can blind pets, damage the environment, and have the potential to severely affect agricultural industries.

The electric ant is native to Central and South America and was first detected in Australia in 2006 in Queensland, where there …

Abridged Submission Guidelines

Professional Agricultural Workers Journal

No abstract provided.

Rabbit Fencing To Protect Crops And Pastures, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

This factsheet outlines the use of fencing to protect crops and pasture from rabbits.

Rabbits cause an estimated loss of $217 million each year to Australian agricultural production and cause significant environmental damage. In Western Australia (WA), areas of native vegetation, particularly on sandy ridges that would otherwise be subject to wind erosion, have been retained on farms. Bush remnants are a major refuge habitat for rabbits, which can cause considerable damage to nearby pastures and crops. A measure of rabbit control can be achieved by poisoning around bush remnants in late summer or autumn, prior to seeding. To be …

Gorse And Its Control, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

Gorse (Ulex europaeus) is a declared pest in Western Australia (WA). This factsheet describes the nature of the plant with links to requirements that landowners/occupiers must adhere to, pest control methods and how to search, detect and report it.

Gorse is a Weed of National Significance (WoNS) present in Australian states and the Australian Capital Territory; it is not present in the Northern Territory. Gorse is a declared pest plant in WA.

European Wasp: Declared Pest, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

The European wasp is one of the worst wasps in the world — harmful to people, outdoor lifestyles, and horticultural and agricultural industries. Early detection of wasp activity is critical to prevent the wasp establishing in Western Australia (WA). This is achieved via collaboration between residents, businesses, industry, and government.

European Wasp Information For Local Government, Department Of Primary Industries And Regional Development, Western Australia

Biosecurity factsheets

The department’s European wasp surveillance and eradication program is a yearly campaign, aimed at detecting the presence of this destructive pest as early as possible so that nests can be found and eradicated.

The continued success of European wasp surveillance and eradication program relies on surveillance in metropolitan Perth and regional areas, strong community awareness, and participation between residents, business owners, community groups, industry, and government.

Safety-Centric Analysis Of Grounding Systems For Substations In Distribution Grids, Fazel Mohammadi, Mahmood Mirhashemi

Electrical & Computer Engineering and Computer Science Faculty Publications

The safety of grounding systems for substations in distribution grids is paramount to ensuring operational reliability, protecting personnel and equipment, and maintaining the stability of distribution grids while complying with regulatory standards. This paper explores essential safety aspects of grounding systems, including fault current handling strategies, the interdependence between protective devices and grounding systems, and maintenance practices. The integration of grounding systems design with overall substation layout and design considerations by focusing on mitigating Ground Potential Rise (GPR) and optimizing bonding techniques, is examined. Additionally, advanced techniques, such as high-frequency grounding and Transient Ground Potential Rise (TGPR) management, are presented …

Global Empirical Model Of Sporadic-E Occurrence Rates, Eli V. Parsch, Anthony L. Franz, Eugene V. Dao, Dong L. Wu, Nimalan Swarnalingam, Cornelius C. J. H. Salinas, Daniel J. Emmons

Faculty Publications

Intense ionization enhancements in the Earth’s ionosphere, known as sporadic-E (E_s), can degrade and severely disrupt the propagation of radio signals. Although many previous studies have analyzed the characteristics and morphologies of sporadic-E, few efforts have attempted to model global E_s occurrence rates (ORs) at high time resolutions. This study develops a global empirical model of blanketing sporadic-E occurrence rates using a Karhunen–Loéve Expansion (KLE) of a global OR climatology built with Global Navigation Satellite System radio occultation (GNSS-RO) and ionosonde observations. Using an fbE ≥ threshold of 3 MHz, the model outputs a blanketing sporadic-E …

Lithicone-Protected Lithium Metal Anodes For Lithium Metal Batteries With Nickel-Rich Cathode Materials, Ridwan A. Ahmed, Kevin V. Carballo, Krishna P. Koirala, Qian Zhao, Peiyuan Gao, Ju-Myung Kim, Cassidy S. Anderson, Xiangbo Meng, Chongmin Wang, Ji-Guang Zhang, Wu Xu

Mechanical Engineering Faculty Publications and Presentations

The high energy density advantage of lithium (Li) metal batteries (LMBs) makes them increasingly desirable; however, problems such as strong reactivity and dendrite growth of Li metal anode limit their practical uses. In this work, a novel Li-containing glycerol (LiGL) or lithicone protection layer on a 50 μm thick Li metal anode is employed for improving the performance of LMBs. This LiGL layer was accurately deposited via a molecular layer deposition (MLD) process at 150°C, using lithium tert-butoxide and glycerol as precursors. The as-formed LiGL coating layer is highly tunable in its thickness by simply adjusting MLD cycles and shows …

Algebraic Structures On Parallelizable Manifolds, Sergey Grigorian

School of Mathematical & Statistical Sciences Faculty Publications

In this paper we explore algebraic and geometric structures that arise on parallelizable manifolds. Given a parallelizable manifold L , there exists a global trivialization of the tangent bundle, which defines a map ρ p : l ⟶ T p L for each point p ∈ L , where l is some vector space. This allows us to define a particular class of vector fields, known as fundamental vector fields, that correspond to each element of l . Furthermore, flows of these vector fields give rise to a product between elements of l and L , which in turn induces …

An Artificial Intelligence-Generated Model Predicts 90-Day Survival In Alcohol-Associated Hepatitis: A Global Cohort Study, Winston Dunn, Yanming Li, Ashwani K Singal, Douglas A Simonetto, Luis A Díaz, Francisco Idalsoaga, Gustavo Ayares, Jorge Arnold, María Ayala-Valverde, Diego Perez, Jaime Gomez, Rodrigo Escarate, Eduardo Fuentes-López, Carolina Ramirez-Cadiz, Dalia Morales-Arraez, Wei Zhang, Steve Qian, Joseph C Ahn, Seth Buryska, Heer Mehta, Nicholas Dunn, Muhammad Waleed, Horia Stefanescu, Andreea Bumbu, Adelina Horhat, Bashar Attar, Rohit Agrawal, Joaquín Cabezas, Victor Echavaría, Berta Cuyàs, Maria Poca, German Soriano, Shiv K Sarin, Rakhi Maiwall, Prasun K Jalal, Fátima Higuera-De-La-Tijera, Anand V Kulkarni, P Nagaraja Rao, Patricia Guerra-Salazar, Lubomir Skladaný, Natália Kubánek, Veronica Prado, Ana Clemente-Sanchez, Diego Rincon, Tehseen Haider, Kristina R Chacko, Gustavo A Romero, Florencia D Pollarsky, Juan C Restrepo, Luis G Toro, Pamela Yaquich, Manuel Mendizabal, Maria L Garrido, Sebastián Marciano, Melisa Dirchwolf, Victor Vargas, César Jiménez, David Hudson, Guadalupe García-Tsao, Guillermo Ortiz, Juan G Abraldes, Patrick S Kamath, Marco Arrese, Vijay H Shah, Ramon Bataller, Juan Pablo Arab

Faculty, Staff and Students Publications

Background and aims: Alcohol-associated hepatitis (AH) poses significant short-term mortality. Existing prognostic models lack precision for 90-day mortality. Utilizing artificial intelligence in a global cohort, we sought to derive and validate an enhanced prognostic model.

Approach and results: The Global AlcHep initiative, a retrospective study across 23 centers in 12 countries, enrolled patients with AH per National Institute for Alcohol Abuse and Alcoholism criteria. Centers were partitioned into derivation (11 centers, 860 patients) and validation cohorts (12 centers, 859 patients). Focusing on 30 and 90-day postadmission mortality, 3 artificial intelligence algorithms (Random Forest, Gradient Boosting Machines, and eXtreme Gradient Boosting) …

School Administrators’ Perspectives On Dyslexia And Transformational Leadership And Implications For Teacher Placement, Christina M. Walker

Electronic Theses and Dissertations

This study focused on the perceptions of secondary-level administrators about dyslexia instruction and their decision-making process in teacher placement within a Texas school district. Using transformative leadership theory, the researcher’s aim was to address the instructional needs of students with dyslexia and help catalyze educational change. The research involved a qualitative descriptive approach to explore administrators’ perspectives and practices. Findings revealed that dyslexia affects approximately 15%–20% of the U.S. population. Despite intellectual capabilities, individuals with dyslexia face persistent struggles in reading and writing because of neurobiological differences. The specific problem addressed was the lack of understanding among school administrators about …

Bridging Gaps. The Role Of School Leaders In Implementing The Mckinney-Vento Act For Homeless Student Success, Brian Jones

Electronic Theses and Dissertations

This qualitative narrative inquiry explores the role of school leaders in implementing the McKinney-Vento Homeless Assistance Act (MKVA) within a public school district in West Texas. The study addresses the challenges school leaders face in supporting homeless students and the strategies they employ to ensure academic success and socio-emotional well-being. Drawing on Bronfenbrenner’s ecological systems theory and Bertalanffy’s general systems theory, the research examines how school leaders' personal understandings and professional experiences influence MKVA provisions' implementation. The study employs semistructured interviews and reflective journals to gather participant data, followed by a member-checking process to enhance the accuracy and credibility of …

Topology And The Quantum Hall Effects, Paul Bracken

School of Mathematical & Statistical Sciences Faculty Publications

The quantum Hall effects are an excellent example of physical systems where topology plays a major role in accounting for the physical observations. It is shown that the conductivity that appears in the quantum Hall effect is a topological invariant. It is illustrated how a fiber bundle over a torus can be constructed producing a geometry in which the system can be referred. The fractional effect can be studied by introducing homotopy and associated braid groups. Filling fractions can be obtained as a consequence of commensurability relations.

Confined Paddock Feeding And Feedlotting Of Sheep, Department Of Primary Industries And Regional Development, Western Australia

Animal production and livestock factsheets

Confinement feeding (also referred to as lot feeding or feedlotting) is an intensive feeding system in a confined area where all, or the majority of, feed and water is supplied to the contained animals. The department recommends using confinement feeding as part of a whole farm livestock, pasture and erosion management program.

We recommend having a confinement feeding system as an integral part of a whole farm livestock, pasture and erosion management program. Guides and resources that provide more detailed information are listed at the bottom of this fact sheet.

Sheep Feed Value Guide, Department Of Primary Industries And Regional Development, Western Australia

Animal production and livestock factsheets

Sheep are supplementary fed for either survival or production purposes. Efficient supplementary feeding should aim to supply sheep with a diet that is sufficient in digestible energy and protein. We recommend testing feedstuffs, although the feed tables supplied here can be used to help roughly estimate the amount of grain and fodder required.

Knowing the value of different feedstuffs is critical when making decisions about livestock nutrition, for survival, maintenance and growth.

Supplementary feeding is a key part of a Western Australian (WA) sheep enterprise because most sheep systems are on annual pasture which is dry over the Mediterranean summer. …

Evaluation Of Dual Purpose Canola And Cereals Grazed With Cattle, Department Of Primary Industries And Regional Development, Western Australia

Animal production and livestock factsheets

The Department of Primary Industries and Regional Development conducted research to investigate and demonstrate the importance of dual-purpose crops (canola, wheat and barley) to improve the feed availability for cattle (in late autumn to early winter) in mixed farming systems of the high rainfall environment of Western Australia (WA).

The grain yield of a wide range of canola and cereal varieties sown in mid-April were unaffected by the grazing of cattle at a stocking rate of 20 to 22 dry sheep equivalent (DSE) per hectare (ha) for up to 4 weeks at Esperance in 2011.

The grazed crops yielded the …